Identification of member connectivity and mass changes on a two-storey framed structure using frequency response functions and artificial neural networks

Abstract This paper presents a structural health monitoring (SHM) technique that utilises pattern changes in frequency response functions (FRFs) as input parameters for a system of artificial neural networks (ANNs) to assess the structural condition of a structure. To verify the proposed method, it is applied to numerical and experimental models of a two-storey framed structure, on which structural damage is induced by member connectivity and mass changes, respectively. For the numerical structure, simulated time-history data are polluted with various levels of white Gaussian noise in order to realistically represent field-testing conditions. As a damage indicator, residual FRFs are used, which are derived by calculating the differences in FRF data between the undamaged/baseline structure and the structure with changed joint conditions or added mass. To obtain suitable patterns for neural network training, principal component analysis (PCA) techniques are adopted to reduce the size of the residual FRF data and to filter noise. A hierarchical system of individual ANNs, termed network ensemble, is then trained to map changes in PCA-reduced residual FRFs to damage conditions. The results obtained for both damage investigations, namely joint damage and mass changes, demonstrate that the proposed SHM technique is accurate and reliable in assessing the condition of the test structure numerically and experimentally based on direct FRF measurements and network ensemble analysis. From the outcomes of the individual networks, it is found that the proposed hierarchical network ensemble approach is highly efficient in filtering poor results of underperforming networks obtained from measurement locations with low damage sensitivity.

[1]  Marek Krawczuk,et al.  The location of a concentrated mass on rectangular plates from measurements of natural vibrations , 2002 .

[2]  Mehmet Imregun,et al.  STRUCTURAL DAMAGE DETECTION USING ARTIFICIAL NEURAL NETWORKS AND MEASURED FRF DATA REDUCED VIA PRINCIPAL COMPONENT PROJECTION , 2001 .

[3]  Bijan Samali,et al.  Dynamic-Based Damage Identification Using Neural Network Ensembles and Damage Index Method , 2010 .

[4]  E. Clothiaux,et al.  Neural Networks and Their Applications , 1994 .

[5]  Bijan Samali,et al.  Location and Severity Identification of Notch-Type Damage in a Two-Storey Steel Framed Structure Utilising Frequency Response Functions and Artificial Neural Network , 2012 .

[6]  D. Tran,et al.  Damage location vector: A non-destructive structural damage detection technique , 2005 .

[7]  Wei Tang,et al.  Ensembling neural networks: Many could be better than all , 2002, Artif. Intell..

[8]  Nuno M. M. Maia,et al.  DAMAGE DETECTION USING THE FREQUENCY-RESPONSE-FUNCTION CURVATURE METHOD , 1999 .

[9]  E. Peter Carden,et al.  EXPERIMENTALLY VALIDATED ADDED MASS IDENTIFICATION ALGORITHM BASED ON FREQUENCY RESPONSE FUNCTIONS , 2004 .

[10]  Tshilidzi Marwala,et al.  DAMAGE IDENTIFICATION USING COMMITTEE OF NEURAL NETWORKS , 2000 .

[11]  James H. Garrett,et al.  Use of neural networks in detection of structural damage , 1992 .

[12]  Alireza Rahai,et al.  Structural model updating using frequency response function and quasi-linear sensitivity equation , 2009 .

[13]  Bijan Samali,et al.  Damage identification in civil engineering structures utilizing PCA‐compressed residual frequency response functions and neural network ensembles , 2011 .

[14]  Daniel J. Inman,et al.  TIME DOMAIN ANALYSIS FOR DAMAGE DETECTION IN SMART STRUCTURES , 1997 .

[15]  Usik Lee,et al.  A frequency response function-based structural damage identification method , 2002 .

[16]  Charles R. Farrar,et al.  FIELD VERIFICATION OF A NONDESTRUCTIVE DAMAGE LOCALIZATION AND SEVERITY ESTIMATION ALGORITHM , 2002 .

[17]  Usik Lee,et al.  A structural damage identification method for plate structures , 2002 .

[18]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[19]  Paul R. White,et al.  Analysis of the maximum likelihood, total least squares and principal component approaches for frequency response function estimation , 2006 .

[20]  Ward Heylen,et al.  Fault localization in structures from remote FRF measurements. Influence of the measurement points , 1998 .

[21]  Arun Kumar Pandey,et al.  Damage detection from changes in curvature mode shapes , 1991 .

[22]  Charles R. Farrar,et al.  Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics: A literature review , 1996 .

[23]  Hoon Sohn,et al.  A review of structural health monitoring literature 1996-2001 , 2002 .

[24]  S. Masri,et al.  Application of Neural Networks for Detection of Changes in Nonlinear Systems , 2000 .

[25]  Anders Krogh,et al.  Learning with ensembles: How overfitting can be useful , 1995, NIPS.

[26]  Bijan Samali,et al.  Structural damage identification utilising PCA-compressed frequency response functions and neural network ensembles , 2008 .

[27]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Michael I. Friswell,et al.  Structural Health Monitoring and Damage Assessment Using Measured FRFs from Multiple Sensors, Part II: Decision Making with RBF Networks , 2003 .

[29]  J. Tang.  Frequency response based damage detection using principal component analysis , 2005, 2005 IEEE International Conference on Information Acquisition.

[30]  Yi-Qing Ni,et al.  Experimental investigation of seismic damage identification using PCA-compressed frequency response functions and neural networks , 2006 .

[31]  Tshilidzi Marwala,et al.  FAULT IDENTIFICATION USING FINITE ELEMENT MODELS AND NEURAL NETWORKS , 1999 .

[32]  Xin Yao,et al.  Making use of population information in evolutionary artificial neural networks , 1998, IEEE Trans. Syst. Man Cybern. Part B.